Measures the asymmetry of a dataset’s distribution — whether values trail off more toward the high end or the low end.
How it works
The third and second moments of the data around its mean are computed, and their ratio (raised to the appropriate power) gives the skewness value.
What this does not include
Several skewness formula variants exist with slightly different sample-adjustment corrections — this calculator uses the simpler population form, the most commonly taught starting definition.
How to use this calculator
- Enter your dataset as comma-separated numbers.
A worked example
Dataset 2, 3, 4, 5, 6, 7, 8, 9, 50 — a tight cluster with one large outlier — has a skewness of 2.3644, a strongly positive value reflecting that long right-hand tail.
Dataset 1, 2, 3, 4, 5 — perfectly symmetric — has a skewness of exactly 0.
What the calculation does
| Term | Meaning |
|---|---|
| m2 (second moment) | Average squared deviation from the mean — the population variance |
| m3 (third moment) | Average cubed deviation from the mean |
| Skewness | m3 ÷ m2^1.5 |
Edge cases worth knowing
Cubing (rather than squaring) the deviations is what lets skewness detect direction, not just spread — a value above the mean cubes to a positive number, one below cubes to a negative number, so they don’t cancel the way squared deviations would.
A dataset needs at least 3 values and some spread to have a defined skewness — with fewer values, or if every value is identical (zero spread), the calculation has nothing to measure.
Frequently asked questions
What does a positive skewness value mean?
The distribution has a longer tail toward higher values — most data clusters on the lower end with a few large outliers pulling the tail rightward.
What does a skewness of zero mean?
The distribution is perfectly symmetric around its mean, like a standard bell curve.
Why does a single large outlier affect skewness so much?
The formula cubes each deviation from the mean, so an extreme outlier’s contribution grows dramatically faster than an ordinary value’s — pulling the whole measure strongly in its direction.
